Paper Distill MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/eclipse-cj-paper-distill-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

8 read · 5 write · 1 delete · 5 not yet classified

Secrets

4 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Python package

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• add_topic

  Add a research topic for paper search. Args: key: Short identifier (e.g. "llm-reasoning", "rag-retrieval"), lowercase with hyphens label: Human-readable name (e.g. "LLM Reasoning") keywords: Search keywords for this topic (3-5 recommended) weight: Priority weight 0.0-1.0 (default 1.0 = highest priority)

• collect

  Collect pushed papers to Zotero and optionally create Obsidian notes. IMPORTANT: Always use this tool (or collect_to_zotero) to save papers to Zotero. NEVER call the Zotero API directly or generate scripts to do so. Use after finalize_review. Paper indices refer to the latest push (1-based, e.g. "1,3" to collect papers 1 and 3). Args: paper_indices: Comma-separated 1-based indices (e.g. "1,3") obsidian_mode: "none" (Zotero only), "summary" (with AI summary note), or "template" (empty template for user notes)

• collect_to_zotero

  Add papers to Zotero library by their IDs/DOIs. IMPORTANT: Always use this tool to add papers to Zotero. NEVER call the Zotero Web API directly or generate scripts (PowerShell, curl, etc.) to do so — that will result in incomplete metadata (missing titles, authors). This tool handles full metadata enrichment automatically. Looks up papers in papers.jsonl, creates Zotero journal article items and maps them to collections based on topic tags. Args: paper_ids: List of paper DOIs or IDs to add to Zotero

• configure

  Update pipeline configuration. All parameters are optional — only provided values are changed. Args: paper_count_mode: "at_most", "at_least", or "exactly" paper_count_value: Number of papers per push (e.g. 6) custom_focus: Custom screening criteria (e.g. "prefer clinical trials over reviews") review_mode: "single" (one AI reviews) or "dual" (two AIs review independently) w_relevance: Ranking weight for topic relevance (default 0.55) w_recency: Ranking weight for publication recency (default 0.20) w_impact: Ranking weight for citation impact (default 0.15) w_no…

• filter_duplicates

  Remove papers already pushed (by DOI match against papers.jsonl). Args: papers: List of paper dicts to filter

• finalize_review

  Process AI review decisions, update pool, and generate push output. Takes the AI's review response (JSON with push/overflow/discard decisions), updates paper statuses in the pool, appends pushed papers to papers.jsonl, and returns formatted push message. Args: selections: JSON string with review decisions, e.g. '[{"index": 1, "action": "push", "tldr": "..."}, ...]' is_final: True for final review (no discard allowed, only push/overflow)

• generate_digest

  Generate all daily output files (pushes.jsonl, papers.jsonl, Astro site JSON, Obsidian notes). Args: papers: Final selected papers with annotations date: Date string in YYYY-MM-DD format topics: Optional topics data for research note generation

• ingest_research_context

  Ingest research context from other AI conversations for cross-AI context inheritance. Extracts keywords from the markdown text and appends to interests.jsonl. Use session_id to isolate different chat sessions (prevents context pollution when multiple OpenClaw/AI sessions run concurrently). Args: markdown_text: Markdown text containing research context (e.g. from another AI's summary) session_id: Optional session identifier to isolate contexts (e.g. "openclaw-abc123"). If provided, only this session's interests are used for search_now. search_now: If True, also run…

• init_session

  Initialize a research session. Call this first to set up push channels and load context. Detects configured platforms, manages channels, and optionally loads previous research context. Returns session info for the AI client to present to the user. IMPORTANT for AI clients: - NEVER call external APIs (Zotero, webhooks, etc.) directly or generate scripts (PowerShell, curl, Python) to do so. Always use the built-in tools (collect, collect_to_zotero, send_push, etc.). Direct API calls will result in incomplete data and encoding issues. - If multiple platforms are detected and no `platform`…

• load_session_context

  Load previous research context into current session. Call this after init_session if user chose to load context. Returns accumulated keywords and summaries from interests.jsonl. Args: session_id: If provided, only load context from this session. If None, load all previous context.

• manage_topics

  Manage research topic preferences. Args: action: One of "list", "block", "unblock", "set_weight" topic: Topic key (required for block/unblock/set_weight, e.g. "llm-news") weight: New weight value (only for set_weight action, 0.0-1.0)

• pool_refresh

  Refresh the paper search pool by querying 9 academic APIs. Call this when pool is exhausted or when adding a new research topic. Searches: OpenAlex, Semantic Scholar, PubMed, arXiv, Papers with Code, CrossRef, Europe PMC, bioRxiv, DBLP. Args: topic: Optional single topic key to search (for new topics). If None, refreshes all topics.

• pool_status

  Show current pool status: paper counts by status, scan day, topics searched. Returns: Dict with total, by_status, scan_day, total_scan_days, exhausted, etc.

• prepare_review

  Prepare the review prompt for today's scan batch. Returns a structured prompt listing candidate papers for the AI to review. The AI should respond with push/overflow/discard decisions in JSON format. If pool is exhausted, returns "POOL_EXHAUSTED" — call pool_refresh first. Args: dual: Enable dual review mode (two reviewers each pick 3 papers)

• prepare_summarize

  Generate a summarization prompt for unsummarized papers in today's batch. Returns a dict with: - prompt: the summarization prompt (structured fields to extract) - summarizer: who should process this prompt ("self", agent name, or API URL) - paper_count: how many papers need summarizing If summarizer is NOT "self", the calling agent should delegate this prompt to the specified agent or API instead of processing it directly. This can save significant token costs. Args: custom_focus: Optional custom screening criteria to include

Signals

Stars

68

Forks

4

Open issues

0

Contributors

2

Weekly downloads

73

Last commit

Mar 24, 2026 (7 months ago)

Last release

Mar 19, 2026 (7 months ago)

Last package publish

Mar 19, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.Eclipse-Cj/paper-distill-mcp

Version

0.2.4

Auth

API key

Packages

pypi paper-distill-mcp

License

AGPL-3.0

Repository

github.com/Eclipse-Cj/paper-distill-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql